mm: kill vma flag VM_CAN_NONLINEAR

Move actual pte filling for non-linear file mappings into the new special
vma operation: ->remap_pages().

Filesystems must implement this method to get non-linear mapping support,
if it uses filemap_fault() then generic_file_remap_pages() can be used.

Now device drivers can implement this method and obtain nonlinear vma support.

Change-Id: Ifbbbdfcdf871a8173856a13087400885357f95ee
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Carsten Otte <cotte@de.ibm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>	#arch/tile
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Eric Paris <eparis@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Morris <james.l.morris@oracle.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Kentaro Takeda <takedakn@nttdata.co.jp>
Cc: Matt Helsley <matthltc@us.ibm.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Venkatesh Pallipadi <venki@google.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/staging/android/ashmem.c

@@ -338,7 +338,6 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 			fput(vma->vm_file);
 		vma->vm_file = asma->file;
 	}
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 	asma->vm_start = vma->vm_start;
 
 out:

fs/9p/vfs_file.c

@@ -735,6 +735,7 @@ v9fs_cached_file_write(struct file *filp, const char __user * data,
 static const struct vm_operations_struct v9fs_file_vm_ops = {
 	.fault = filemap_fault,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
+	.remap_pages = generic_file_remap_pages,
 };
 
 

fs/btrfs/file.c

@@ -1581,6 +1581,7 @@ out:
 static const struct vm_operations_struct btrfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.page_mkwrite	= btrfs_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 };
 
 static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
@@ -1592,7 +1593,6 @@ static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
 
 	file_accessed(filp);
 	vma->vm_ops = &btrfs_file_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 
 	return 0;
 }

fs/ceph/addr.c

@@ -1234,6 +1234,7 @@ out:
 static struct vm_operations_struct ceph_vmops = {
 	.fault		= filemap_fault,
 	.page_mkwrite	= ceph_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 };
 
 int ceph_mmap(struct file *file, struct vm_area_struct *vma)
@@ -1244,6 +1245,5 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &ceph_vmops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }

fs/cifs/file.c

@@ -2611,6 +2611,7 @@ cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 static struct vm_operations_struct cifs_file_vm_ops = {
 	.fault = filemap_fault,
 	.page_mkwrite = cifs_page_mkwrite,
+	.remap_pages = generic_file_remap_pages,
 };
 
 int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)

fs/ext4/file.c

@@ -144,6 +144,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= filemap_fault,
 	.page_mkwrite   = ext4_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 };
 
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
@@ -154,7 +155,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &ext4_file_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
 

fs/fuse/file.c

@@ -1421,6 +1421,7 @@ static const struct vm_operations_struct fuse_file_vm_ops = {
 	.close		= fuse_vma_close,
 	.fault		= filemap_fault,
 	.page_mkwrite	= fuse_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 };
 
 static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)

fs/gfs2/file.c

@@ -469,6 +469,7 @@ out:
 static const struct vm_operations_struct gfs2_vm_ops = {
 	.fault = filemap_fault,
 	.page_mkwrite = gfs2_page_mkwrite,
+	.remap_pages = generic_file_remap_pages,
 };
 
 /**
@@ -503,7 +504,6 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
 			return error;
 	}
 	vma->vm_ops = &gfs2_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 
 	return 0;
 }

fs/nfs/file.c

@@ -553,6 +553,7 @@ out:
 static const struct vm_operations_struct nfs_file_vm_ops = {
 	.fault = filemap_fault,
 	.page_mkwrite = nfs_vm_page_mkwrite,
+	.remap_pages = generic_file_remap_pages,
 };
 
 static int nfs_need_sync_write(struct file *filp, struct inode *inode)

fs/nilfs2/file.c

@@ -126,13 +126,13 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 static const struct vm_operations_struct nilfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.page_mkwrite	= nilfs_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 };
 
 static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	file_accessed(file);
 	vma->vm_ops = &nilfs_file_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
 

fs/ocfs2/mmap.c

@@ -171,6 +171,7 @@ out:
 static const struct vm_operations_struct ocfs2_file_vm_ops = {
 	.fault		= ocfs2_fault,
 	.page_mkwrite	= ocfs2_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 };
 
 int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
@@ -186,7 +187,6 @@ int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
 	ocfs2_inode_unlock(file->f_dentry->d_inode, lock_level);
 out:
 	vma->vm_ops = &ocfs2_file_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
 

fs/sdcardfs/file.c

@@ -205,7 +205,6 @@ static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma)
 	 */
 	file_accessed(file);
 	vma->vm_ops = &sdcardfs_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 
 	file->f_mapping->a_ops = &sdcardfs_aops; /* set our aops */
 	if (!SDCARDFS_F(file)->lower_vm_ops) /* save for our ->fault */

fs/sdcardfs/mmap.c

@@ -85,6 +85,7 @@ const struct address_space_operations sdcardfs_aops = {
 const struct vm_operations_struct sdcardfs_vm_ops = {
 	.fault		= sdcardfs_fault,
 	.page_mkwrite	= sdcardfs_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 	.open		= sdcardfs_vm_open,
 	.close		= sdcardfs_vm_close,
 };

fs/ubifs/file.c

@@ -1536,6 +1536,7 @@ out_unlock:
 static const struct vm_operations_struct ubifs_file_vm_ops = {
 	.fault        = filemap_fault,
 	.page_mkwrite = ubifs_vm_page_mkwrite,
+	.remap_pages = generic_file_remap_pages,
 };
 
 static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma)

fs/xfs/xfs_file.c

@@ -990,7 +990,6 @@ xfs_file_mmap(
 	struct vm_area_struct *vma)
 {
 	vma->vm_ops = &xfs_file_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 
 	file_accessed(filp);
 	return 0;
@@ -1044,4 +1043,5 @@ const struct file_operations xfs_dir_file_operations = {
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.page_mkwrite	= xfs_vm_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
 };

include/linux/fs.h

@@ -2459,6 +2459,8 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
+extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
+		unsigned long size, pgoff_t pgoff);
 extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);

include/linux/mm.h

@@ -128,7 +128,6 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_INSERTPAGE	0x02000000	/* The vma has had "vm_insert_page()" done on it */
 #define VM_NODUMP	0x04000000	/* Do not include in the core dump */
 
-#define VM_CAN_NONLINEAR 0x08000000	/* Has ->fault & does nonlinear pages */
 #define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
 #define VM_SAO		0x20000000	/* Strong Access Ordering (powerpc) */
 #define VM_PFN_AT_MMAP	0x40000000	/* PFNMAP vma that is fully mapped at mmap time */
@@ -196,8 +195,7 @@ static inline int is_pfn_mapping(struct vm_area_struct *vma)
  * of VM_FAULT_xxx flags that give details about how the fault was handled.
  *
  * pgoff should be used in favour of virtual_address, if possible. If pgoff
- * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear
- * mapping support.
+ * is used, one may implement ->remap_pages to get nonlinear mapping support.
  */
 struct vm_fault {
 	unsigned int flags;		/* FAULT_FLAG_xxx flags */
@@ -255,6 +253,9 @@ struct vm_operations_struct {
 	int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
 		const nodemask_t *to, unsigned long flags);
 #endif
+	/* called by sys_remap_file_pages() to populate non-linear mapping */
+	int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr,
+			   unsigned long size, pgoff_t pgoff);
 };
 
 struct mmu_gather;

mm/filemap.c

@@ -1753,6 +1753,7 @@ EXPORT_SYMBOL(filemap_fault);
 
 const struct vm_operations_struct generic_file_vm_ops = {
 	.fault		= filemap_fault,
+	.remap_pages	= generic_file_remap_pages,
 };
 
 /* This is used for a general mmap of a disk file */
@@ -1765,7 +1766,6 @@ int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &generic_file_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
 

mm/filemap_xip.c

@@ -304,6 +304,7 @@ out:
 
 static const struct vm_operations_struct xip_file_vm_ops = {
 	.fault	= xip_file_fault,
+	.remap_pages = generic_file_remap_pages,
 };
 
 int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
@@ -312,7 +313,7 @@ int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
 
 	file_accessed(file);
 	vma->vm_ops = &xip_file_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR | VM_MIXEDMAP;
+	vma->vm_flags |= VM_MIXEDMAP;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xip_file_mmap);

mm/fremap.c

@@ -5,6 +5,7 @@
  *
  * started by Ingo Molnar, Copyright (C) 2002, 2003
  */
+#include <linux/export.h>
 #include <linux/backing-dev.h>
 #include <linux/mm.h>
 #include <linux/swap.h>
@@ -80,9 +81,10 @@ out:
 	return err;
 }
 
-static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
-			unsigned long addr, unsigned long size, pgoff_t pgoff)
+int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
+			     unsigned long size, pgoff_t pgoff)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	int err;
 
 	do {
@@ -95,9 +97,9 @@ static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
 		pgoff++;
 	} while (size);
 
-        return 0;
-
+	return 0;
 }
+EXPORT_SYMBOL(generic_file_remap_pages);
 
 /**
  * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma
@@ -167,7 +169,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
 		goto out;
 
-	if (!(vma->vm_flags & VM_CAN_NONLINEAR))
+	if (!vma->vm_ops->remap_pages)
 		goto out;
 
 	if (start < vma->vm_start || start + size > vma->vm_end)
@@ -229,7 +231,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	}
 
 	mmu_notifier_invalidate_range_start(mm, start, start + size);
-	err = populate_range(mm, vma, start, size, pgoff);
+	err = vma->vm_ops->remap_pages(vma, start, size, pgoff);
 	mmu_notifier_invalidate_range_end(mm, start, start + size);
 	if (!err && !(flags & MAP_NONBLOCK)) {
 		if (vma->vm_flags & VM_LOCKED) {

mm/mmap.c

@@ -698,8 +698,7 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma,
 			struct file *file, unsigned long vm_flags,
 			const char __user *anon_name)
 {
-	/* VM_CAN_NONLINEAR may get set later by f_op->mmap() */
-	if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR)
+	if (vma->vm_flags ^ vm_flags)
 		return 0;
 	if (vma->vm_file != file)
 		return 0;

mm/nommu.c

@@ -2002,6 +2002,14 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
+int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
+			     unsigned long size, pgoff_t pgoff)
+{
+	BUG();
+	return 0;
+}
+EXPORT_SYMBOL(generic_file_remap_pages);
+
 static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long addr, void *buf, int len, int write)
 {

mm/shmem.c

@@ -1235,7 +1235,6 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	file_accessed(file);
 	vma->vm_ops = &shmem_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
 
@@ -2665,6 +2664,7 @@ static const struct vm_operations_struct shmem_vm_ops = {
 	.set_policy     = shmem_set_policy,
 	.get_policy     = shmem_get_policy,
 #endif
+	.remap_pages	= generic_file_remap_pages,
 };
 
 static struct dentry *shmem_mount(struct file_system_type *fs_type,
@@ -2853,7 +2853,6 @@ void shmem_set_file(struct vm_area_struct *vma, struct file *file)
 		fput(vma->vm_file);
 	vma->vm_file = file;
 	vma->vm_ops = &shmem_vm_ops;
-	vma->vm_flags |= VM_CAN_NONLINEAR;
 }
 
 /**